Paul Smolensky

18.3k total citations · 4 hit papers
109 papers, 6.7k citations indexed

About

Paul Smolensky is a scholar working on Artificial Intelligence, Experimental and Cognitive Psychology and Language and Linguistics. According to data from OpenAlex, Paul Smolensky has authored 109 papers receiving a total of 6.7k indexed citations (citations by other indexed papers that have themselves been cited), including 56 papers in Artificial Intelligence, 17 papers in Experimental and Cognitive Psychology and 17 papers in Language and Linguistics. Recurrent topics in Paul Smolensky's work include Natural Language Processing Techniques (35 papers), Topic Modeling (18 papers) and Syntax, Semantics, Linguistic Variation (17 papers). Paul Smolensky is often cited by papers focused on Natural Language Processing Techniques (35 papers), Topic Modeling (18 papers) and Syntax, Semantics, Linguistic Variation (17 papers). Paul Smolensky collaborates with scholars based in United States, United Kingdom and Netherlands. Paul Smolensky's co-authors include Alan Prince, Bruce Tesar, Michael C. Mozer, Géraldine Légendre, Jennifer Culbertson, Yoshiro Miyata, Matthew Goldrick, D. Weingarten, B. Freedman and Iris Berent and has published in prestigious journals such as Science, Proceedings of the National Academy of Sciences and Physics Letters B.

In The Last Decade

Paul Smolensky

102 papers receiving 5.7k citations

Hit Papers

On the proper treatment of connectionism 1986 2026 1999 2012 1988 1986 1990 2004 250 500 750 1000

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Paul Smolensky United States 32 3.4k 2.0k 1.4k 1.2k 1.1k 109 6.7k
Mark Steedman United Kingdom 48 6.4k 1.9× 1.2k 0.6× 1.3k 0.9× 1.8k 1.5× 888 0.8× 209 9.3k
Frank Keller United Kingdom 36 3.0k 0.9× 1.1k 0.6× 1.9k 1.4× 1.1k 0.9× 1.4k 1.4× 148 6.1k
Luc Steels Belgium 41 2.6k 0.8× 686 0.3× 595 0.4× 735 0.6× 467 0.4× 209 5.5k
Daniel Jurafsky United States 40 8.7k 2.6× 955 0.5× 577 0.4× 908 0.8× 584 0.6× 95 10.9k
Julia Hirschberg United States 55 7.8k 2.3× 4.3k 2.2× 722 0.5× 2.3k 1.9× 599 0.6× 324 12.1k
Noah D. Goodman United States 46 3.4k 1.0× 1.1k 0.6× 1.8k 1.3× 760 0.6× 2.6k 2.5× 203 8.2k
Richard Sproat United States 35 3.8k 1.1× 1.1k 0.5× 253 0.2× 669 0.6× 256 0.2× 160 4.9k
Robert M. Nosofsky United States 49 3.5k 1.0× 3.5k 1.7× 5.6k 4.1× 291 0.2× 6.0k 5.7× 141 12.2k
Mark A. Pitt United States 42 1.5k 0.4× 1.9k 0.9× 2.0k 1.5× 156 0.1× 915 0.9× 150 5.2k
Marco Baroni Italy 40 5.8k 1.7× 547 0.3× 638 0.5× 630 0.5× 371 0.4× 128 7.0k

Countries citing papers authored by Paul Smolensky

Since Specialization
Citations

This map shows the geographic impact of Paul Smolensky's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Paul Smolensky with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Paul Smolensky more than expected).

Fields of papers citing papers by Paul Smolensky

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Paul Smolensky. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Paul Smolensky. The network helps show where Paul Smolensky may publish in the future.

Co-authorship network of co-authors of Paul Smolensky

This figure shows the co-authorship network connecting the top 25 collaborators of Paul Smolensky. A scholar is included among the top collaborators of Paul Smolensky based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Paul Smolensky. Paul Smolensky is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
McCoy, R. Thomas, Paul Smolensky, Tal Linzen, Jianfeng Gao, & Aslı Çelikyılmaz. (2023). How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVEN. Transactions of the Association for Computational Linguistics. 11. 652–670. 23 indexed citations
2.
Smolensky, Paul, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, & Jianfeng Gao. (2022). Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems. AI Magazine. 43(3). 308–322. 27 indexed citations
3.
Smolensky, Paul, Eric Rosen, & Matthew Goldrick. (2020). Learning a gradient grammar of French liaison. Proceedings of the Annual Meetings on Phonology. 8. 8 indexed citations
4.
Palangi, Hamid, Paul Smolensky, Xiaodong He, & Li Deng. (2017). Deep Learning of Grammatically-Interpretable Representations Through Question-Answering.. arXiv (Cornell University). 6 indexed citations
5.
Huang, Qiuyuan, Paul Smolensky, Xiaodong He, Li Deng, & Dapeng Wu. (2017). A Neural-Symbolic Approach to Natural Language Tasks.. arXiv (Cornell University). 2 indexed citations
6.
Palangi, Hamid, Qiuyuan Huang, Paul Smolensky, Xiaodong He, & Li Deng. (2017). Grammatically-Interpretable Learned Representations in Deep NLP Models. Neural Information Processing Systems. 1 indexed citations
7.
Smolensky, Paul. (2012). Symbolic functions from neural computation. Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences. 370(1971). 3543–3569. 14 indexed citations
8.
Culbertson, Jennifer & Paul Smolensky. (2012). A Bayesian Model of Biases in Artificial Language Learning: The Case of a Word‐Order Universal. Cognitive Science. 36(8). 1468–1498. 20 indexed citations
9.
Smolensky, Paul & Géraldine Légendre. (2006). Linguistic and philosophical implications. MIT Press eBooks. 5 indexed citations
10.
Smolensky, Paul & Géraldine Légendre. (2006). The Harmonic Mind: From Neural Computation to Optimality-Theoretic GrammarVolume I: Cognitive Architecture (Bradford Books). The MIT Press eBooks. 29 indexed citations
11.
Smolensky, Paul. (2005). An fMRI Study of the Effects of Memory and Goal Setting in a Risk Taking Task. eScholarship (California Digital Library). 27(27). 1 indexed citations
12.
Smolensky, Paul. (2002). Optimality Theory: Frequently Asked 'Questions'. 91–98. 1 indexed citations
13.
Hale, John & Paul Smolensky. (2001). A Parser for Harmonic Context-Free Grammars. eScholarship (California Digital Library). 23(23). 2 indexed citations
14.
Smolensky, Paul. (1996). On the comprehension/production dilemma in child language. Linguistic Inquiry. 27(4). 720–732. 171 indexed citations
15.
Smolensky, Paul, et al.. (1993). Integrating connectionist and symbolic computation for the theory of language. Current Science. 64(6). 381–391. 10 indexed citations
16.
Mozer, Michael C., et al.. (1993). Dynamic Conflict Resolution in a Connectionist Rule-Based System.. International Joint Conference on Artificial Intelligence. 1366–1373. 3 indexed citations
17.
Mozer, Michael C., et al.. (1991). The Connectionist Scientist Game: Rule Extraction and Refinement in a Neural Network. eScholarship (California Digital Library). 11 indexed citations
18.
Légendre, Géraldine, Yoshiro Miyata, & Paul Smolensky. (1990). Distributed Recursive Structure Processing. Neural Information Processing Systems. 47–53. 5 indexed citations
19.
Smolensky, Paul. (1986). Information processing in dynamical systems: foundations of harmony theory. MIT Press eBooks. 194–281. 976 indexed citations breakdown →
20.
Smolensky, Paul. (1983). Schema selection and stochastic inference in modular environments. National Conference on Artificial Intelligence. 378–382. 48 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026